© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35734
    Prev
    Next
    INDEX
    Explanations

    substitution or replacement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ວ
    0.39
     Cucumber
    0.38
     Pray
    0.37
    ுறு
    0.36
     Dull
    0.35
     dư
    0.35
    撬
    0.35
     perj
    0.34
     inol
    0.34
     ä
    0.34
    POSITIVE LOGITS
     вместо
    0.46
     barato
    0.44
     แทน
    0.43
     statt
    0.43
     마치
    0.42
    instead
    0.42
     erset
    0.42
     대신
    0.40
     instead
    0.40
     equivalent
    0.39
    Activations Density 0.086%

    No Known Activations